Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ost

    np_max-act · gemini-2.0-flash

    The neuron specifically detects occurrences of the term “homeostasis” (and its variants like “homeostatic”) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    풍
    -0.07
     сила
    -0.06
     prenatal
    -0.06
    (options
    -0.06
     Deliver
    -0.06
    頭
    -0.06
     theoretical
    -0.06
    脑
    -0.06
     دوران
    -0.06
     trials
    -0.06
    POSITIVE LOGITS
    uffled
    0.07
     часов
    0.07
     lider
    0.07
    UnitOfWork
    0.06
     meny
    0.06
    !!!↵↵
    0.06
    ा↵↵
    0.06
     toilet
    0.06
     hodin
    0.06
    ROTO
    0.06
    Act Density 0.003%

    No Known Activations